Dynamic control system for rare earth extraction process based on data acquisition

Abstract

The present invention relates to the technical field of intelligent control of rare earth extraction processes, and specifically discloses a dynamic control system for rare earth extraction process control based on data acquisition. The system comprises a real-time monitoring and division module for emulsification risk, a high-risk early warning processing module, and a low-risk area emulsification trend prediction and adaptive control module. Interfacial tension and turbidity data are collected by high-precision sensors, and features are extracted by combining empirical mode decomposition and empirical wavelet transform to construct emulsification trend characteristic values ​​and divide risk areas. A support vector machine regression prediction model is established for low-risk area data to achieve quantitative prediction of emulsification development trends. When the prediction score exceeds a limit, a fuzzy PID algorithm is used to dynamically adjust the stirring rate, phase flow rate, and demulsifier addition amount to achieve closed-loop optimization control of the extraction process.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of rare earth extraction process, and in particular to a dynamic control system for rare earth extraction process control based on data acquisition. Background Art

[0002] In the rare earth extraction process, solvent extraction is a key separation and purification step and is widely used in industrial production. In this process, the organic phase and the aqueous phase are fully contacted in the mixing tank to achieve the selective transfer of metal ions, and then enter the clarification stage to complete the phase separation. However, in actual operation, due to factors such as stirring intensity, changes in phase composition, and interference from impurity ions, emulsification can easily occur, making it difficult to effectively separate the two phases, thereby affecting mass transfer efficiency, reducing extraction efficiency, and even causing process interruption. Therefore, how to achieve real-time monitoring, accurate identification, and dynamic regulation of emulsification trends has become a technical problem that needs to be solved urgently to improve the stability and automation level of the rare earth extraction process.

[0003] Existing systems typically use traditional time-domain or frequency-domain methods for feature extraction, which struggles to effectively capture the nonlinear and non-stationary characteristics of early emulsification signals. This results in delayed emulsification state identification and a high rate of misjudgment. In particular, traditional methods lack sufficient early warning time and accuracy for identifying trends transitioning from low-risk to high-risk areas. This hinders early intervention and adaptive adjustments in control strategies, impacting the stability and safety of overall process operations. Summary of the Invention

[0004] The purpose of the present invention is to provide a dynamic control system for rare earth extraction process control based on data acquisition to solve the above-mentioned problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The dynamic control system for rare earth extraction process control based on data acquisition includes:

[0007] An emulsification risk real-time monitoring and classification module is used to collect real-time interfacial tension data and turbidity data of the mixed phase during the rare earth extraction process, dynamically analyze the data in the control system, and divide the process nodes into high emulsification risk areas and low emulsification risk areas based on the analysis results;

[0008] A high-risk early warning processing module, which triggers a real-time early warning mechanism based on high emulsification risk areas;

[0009] A low-risk area emulsification trend prediction and adaptive control module, which extracts interfacial tension anomaly characteristic values ​​and turbidity fluctuation characteristic values ​​of the mixed phase during the rare earth extraction process based on the low emulsification risk area, constructs the interfacial tension anomaly characteristic values ​​and turbidity fluctuation characteristic values ​​into a comprehensive risk characteristic vector, and inputs the vector into the emulsification development trend prediction model for analysis. The module predicts the future emulsification development trend and dynamically adjusts the extraction operating parameters based on the prediction results to achieve adaptive optimization control of the extraction process;

[0010] The extraction operation parameters include stirring rate, phase flow rate and demulsifier addition amount.

[0011] As a further solution of the present invention: the dynamic analysis of data in the control system specifically includes:

[0012] Conduct trend analysis on interfacial tension and calculate abnormal characteristic value of interfacial tension based on its variation range;

[0013] According to the change of the turbidity of the mixed phase, the turbidity fluctuation characteristic value is calculated;

[0014] The interfacial tension anomaly characteristic value and the turbidity fluctuation characteristic value are normalized and calculated to obtain the emulsification trend characteristic value, which is used to divide the process nodes into high emulsification risk areas and low emulsification risk areas.

[0015] As a further solution of the present invention: the process of obtaining the abnormal characteristic value of the interfacial tension is:

[0016] Obtain real-time interfacial tension time series data during rare earth extraction;

[0017] performing empirical mode decomposition on the interfacial tension time series to adaptively decompose it into a plurality of intrinsic mode function components and a trend residual term;

[0018] Perform Hilbert transform on each intrinsic mode function component, construct an analytical signal and extract the instantaneous amplitude and instantaneous frequency information, and then calculate the energy density distribution of each intrinsic mode function;

[0019] Select the energy fluctuation trend The intrinsic mode functions are calculated, and the difference between the maximum and minimum energy density of these intrinsic mode functions is calculated to obtain the energy density deviation value. The energy density deviation value is compared with the selected previous The energy mean of the intrinsic mode functions is calculated by ratio, and the abnormal characteristic value of the interfacial tension is obtained.

[0020] As a further solution of the present invention: the process of obtaining the turbidity fluctuation characteristic value is:

[0021] Obtaining real-time mixed phase turbidity time series data during rare earth extraction;

[0022] The mixed phase turbidity time series data were decomposed by empirical wavelet transform to obtain a set of intrinsic mode components.

[0023] Select multiple modal components reflecting turbidity fluctuation characteristics and calculate the energy distribution of the selected modal components;

[0024] The energy distribution of each selected natural mode component is ratioed to the total energy distribution of all selected natural mode components to obtain the energy ratio of each selected natural mode component. The energy ratios of all selected natural mode components are summed to obtain the turbidity fluctuation characteristic value.

[0025] As a further solution of the present invention: the process nodes are divided into high emulsification risk areas and low emulsification risk areas, specifically including:

[0026] Determine whether the emulsification trend characteristic value of each process node is greater than or equal to the preset threshold. If so, it is recorded as a high emulsification risk area; if not, it is recorded as a low emulsification risk area.

[0027] As a further solution of the present invention: the interfacial tension abnormality characteristic value and the turbidity fluctuation characteristic value are constructed into a comprehensive risk characteristic vector, and input into the emulsification development trend prediction model for analysis, specifically including:

[0028] The interfacial tension anomaly characteristic value and turbidity fluctuation characteristic value of the low emulsification risk area are obtained, and the interfacial tension anomaly characteristic value and the turbidity fluctuation characteristic value are constructed into a comprehensive risk characteristic vector as the input of the emulsification development trend prediction model to minimize the error between the predicted emulsification risk score and the actual emulsification risk score. The emulsification development trend prediction model is used as the prediction target, and the emulsification development trend model is trained. According to the trained emulsification development trend model, the predicted emulsification risk score is output. The emulsification development trend model is a support vector machine model.

[0029] As a further solution of the present invention: the training process of the emulsification development trend prediction model is:

[0030] During the model training phase, the interfacial tension anomaly characteristic values ​​and turbidity fluctuation characteristic values ​​of low-risk areas are first extracted from historical data and constructed into a comprehensive risk characteristic vector as model input; the actual historical emulsification risk score is used as the model output label, and the support vector machine regression algorithm is adopted with the radial basis function as the kernel function. By adjusting the penalty coefficient, kernel parameters and error tolerance, the optimal regression model is constructed. The goal is to minimize the error between the emulsification risk score predicted by the model and the actual score. The cross-validation strategy is introduced during the training process to optimize the hyperparameters, and the mean square error and determination coefficient indicators are used to evaluate the model performance. The trained support vector machine model is deployed to the control system, which receives the collected feature data in real time and outputs a predicted score for future emulsification risks, thereby realizing intelligent prediction and dynamic regulation of the emulsification phenomenon in the rare earth extraction process.

[0031] As a further solution of the present invention: the prediction of future emulsification development trends specifically includes:

[0032] Determine whether the future emulsification risk score is greater than or equal to a preset threshold. If so, the future emulsification risk has a trend of changing from a low emulsification risk to a high emulsification risk. If not, the future emulsification risk does not have a trend of changing from a low emulsification risk to a high emulsification risk.

[0033] The method of dynamically adjusting the extraction operating parameters according to the prediction results to achieve adaptive optimization control of the extraction process specifically includes:

[0034] If the emulsification risk score output by the emulsification development trend prediction model is greater than or equal to the set threshold, the system automatically triggers the adaptive control mechanism to dynamically adjust the three key operating parameters: stirring rate, phase flow rate and demulsifier addition amount. Among them, the stirring rate is reduced in a step-by-step manner according to the rising trend of emulsification risk to reduce interphase disturbance and inhibit the formation of emulsion droplets. The phase flow rate is linearly adjusted according to the trend of abnormal interfacial tension changes to maintain two-phase flow balance. The demulsifier addition amount establishes a feedback control strategy based on the turbidity fluctuation characteristic value and the historical demulsification effect, and the addition ratio is increased as needed to enhance the demulsification efficiency.

[0035] Beneficial effects of the present invention:

[0036] (1) The present invention constructs an emulsification trend characteristic value with physical significance and engineering interpretability by integrating two key process parameters: interfacial tension anomaly characteristic value and turbidity fluctuation characteristic value. On this basis, the system realizes the dynamic identification of the emulsification state and risk area division in the rare earth extraction process. Specifically, the system uses the empirical mode decomposition method to adaptively decompose the interfacial tension time series, extracts the energy density characteristics of each order intrinsic mode function, and obtains the interfacial tension anomaly characteristic value by calculating the ratio of energy fluctuation deviation to mean, thereby effectively capturing the trend of the stability change of the two-phase interface. At the same time, the turbidity signal is subjected to frequency domain modal decomposition using the empirical wavelet transform, and the modal component reflecting the main characteristics of the turbidity fluctuation of the mixed phase is selected. The turbidity fluctuation characteristic value is calculated based on its energy distribution ratio, further enhancing the sensitivity to small disturbances in the early stage of emulsification. After the above two characteristic values ​​are normalized, they are weighted and fused according to a preset ratio to form a comprehensive emulsification trend characteristic value, which serves as the basis for determining the emulsification risk state of the process node. This method not only overcomes the lag and uncertainty problems brought about by traditional reliance on a single parameter or manual experience judgment, but also improves the accuracy, sensitivity and real-time response capability of emulsification risk identification through the introduction of multi-source feature fusion and advanced signal processing methods, providing solid data support and decision-making basis for the implementation of subsequent early warning and control strategies.

[0037] (2) The present invention constructs an emulsification development trend prediction model based on support vector machine regression, fully exploiting the nonlinear mapping relationship between the interfacial tension anomaly characteristic value and the turbidity fluctuation characteristic value in the historical data of low emulsification risk areas to achieve high-precision prediction of future emulsification risk scores. During the model training phase, the system uses the extracted comprehensive risk characteristic vector as the input variable and the actual emulsification risk score generated by expert evaluation or historical records as the output label. It uses the radial basis function as the kernel function and optimizes the penalty coefficient kernel parameter and hyperparameters such as error tolerance through a cross-validation strategy to construct a regression model with strong generalization ability. The model aims to minimize the mean square error between the predicted score and the actual score, and can accurately capture the development direction of the emulsification trend under complex working conditions.

[0038] When the emulsification risk score predicted by the model approaches or exceeds the set threshold, the system automatically triggers the adaptive control mechanism and combines the fuzzy PID control algorithm to coordinately optimize and adjust key operating parameters such as stirring rate, phase flow rate and demulsifier addition amount. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The present invention will be further described below with reference to the accompanying drawings.

[0040] Figure 1 It is a flow chart of the dynamic control system for rare earth extraction process control based on data acquisition of the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0042] See also Figure 1 As shown, the present invention is a dynamic control system for rare earth extraction process control based on data acquisition, comprising:

[0043] An emulsification risk real-time monitoring and classification module is used to collect real-time interfacial tension data and turbidity data of the mixed phase during the rare earth extraction process, dynamically analyze the data in the control system, and divide the process nodes into high emulsification risk areas and low emulsification risk areas based on the analysis results;

[0044] A high-risk early warning processing module, which triggers a real-time early warning mechanism based on high emulsification risk areas;

[0045] A low-risk area emulsification trend prediction and adaptive control module, which extracts interfacial tension anomaly characteristic values ​​and turbidity fluctuation characteristic values ​​of the mixed phase during the rare earth extraction process based on the low emulsification risk area, constructs the interfacial tension anomaly characteristic values ​​and turbidity fluctuation characteristic values ​​into a comprehensive risk characteristic vector, and inputs the vector into the emulsification development trend prediction model for analysis. The module predicts the future emulsification development trend and dynamically adjusts the extraction operating parameters based on the prediction results to achieve adaptive optimization control of the extraction process;

[0046] The extraction operation parameters include stirring rate, phase flow rate and demulsifier addition amount.

[0047] In the real-time monitoring and classification module for emulsification risk, interfacial tension data and turbidity data of the mixed phase during the rare earth extraction process are collected in real time. The data is dynamically analyzed in the control system. Based on the analysis results, the process nodes are divided into high-emulsification risk areas and low-emulsification risk areas. Specifically, the following are included:

[0048] During the rare earth extraction process, real-time acquisition of interfacial tension data is achieved through a high-precision interfacial tension sensor installed in the mixing tank. The interfacial tension sensor adopts an online measurement device based on the capillary rise method, which can continuously obtain time series signals of the two-phase interfacial tension changing with time; the sensor is communicated with the control system, converts the collected analog signals into digital signals, and performs filtering and temperature compensation processing to improve measurement accuracy and stability.

[0049] The turbidity data of the mixed phase is monitored online by an optical turbidity detector installed at the outlet of the mixed phase. The turbidity detector uses a scattered light method (such as a 90° scattering angle) to measure the light scattering intensity caused by suspended particles in the mixed liquid, thereby obtaining a dynamic response curve of turbidity changes over time; the collected turbidity signal is transmitted to the control system via the signal amplification module and the A / D conversion module for subsequent feature extraction and emulsification state evaluation.

[0050] Conduct trend analysis on interfacial tension and calculate abnormal characteristic value of interfacial tension based on its variation range;

[0051] According to the change of the mixed phase turbidity, the turbidity fluctuation characteristic value is calculated;

[0052] The interfacial tension anomaly characteristic value and the turbidity fluctuation characteristic value are normalized and calculated to obtain the emulsification trend characteristic value, which is used to divide the process node into high emulsification risk area and low emulsification risk area;

[0053] The calculation expression of the emulsification tendency characteristic value is: ;

[0054] Where, represents the characteristic value of emulsification tendency, represents the abnormal characteristic value of interfacial tension, represents the characteristic value of turbidity fluctuation, and represents the preset scale factor, and and Both are greater than 0.

[0055] The process of obtaining the abnormal characteristic value of interfacial tension is as follows:

[0056] Obtain real-time interfacial tension time series data during rare earth extraction;

[0057] performing empirical mode decomposition on the interfacial tension time series to adaptively decompose it into a plurality of intrinsic mode function components and a trend residual term;

[0058] Perform Hilbert transform on each intrinsic mode function component, construct an analytical signal and extract the instantaneous amplitude and instantaneous frequency information, and then calculate the energy density distribution of each intrinsic mode function;

[0059] The calculation expression of the analytical signal is: ;

[0060] The calculation expression of the instantaneous amplitude is: ;

[0061] Among them, the calculation expression of instantaneous frequency is: ;

[0062] The calculation expression of energy density is: ;

[0063] Where, Indicates the The analytical signal of the intrinsic mode function, Indicates the The instantaneous amplitude of the intrinsic mode function, represents the complex exponential function, represents the imaginary unit, Indicates the The instantaneous phase of the intrinsic mode function, Indicates the The real part signal of the intrinsic mode function, For the The Hilbert transform results of the intrinsic mode functions represent the orthogonal components of the signal, represents the number of intrinsic mode functions, Indicates the instantaneous phase About Time The derivative of Indicates time, Indicates the The instantaneous frequency of the natural mode function;

[0064] Select the front of the main fluctuation trend of energy The intrinsic mode functions are calculated, and the difference between the maximum and minimum energy density of these intrinsic mode functions is calculated to obtain the energy density deviation value. The energy density deviation value is compared with the selected previous The energy mean of the intrinsic mode functions is calculated by ratio, and the abnormal characteristic value of the interfacial tension is obtained.

[0065] The acquisition process of the turbidity fluctuation characteristic value is:

[0066] Obtaining real-time mixed phase turbidity time series data during rare earth extraction;

[0067] The mixed phase turbidity time series data is decomposed by empirical wavelet transform to obtain a set of intrinsic mode components. The calculation expression is:

[0068] ;

[0069] Where, Indicates the The intrinsic modal components, represents the inverse Fourier transform, represents the spectrum of mixed-phase turbidity time series data, Indicates the filter functions, Indicates time, represents a frequency variable;

[0070] Select multiple modal components that reflect the main fluctuation characteristics of turbidity and calculate the energy distribution of the selected modal components. The calculation expression is: ;

[0071] Where, Indicates the The energy distribution of the selected natural mode components, Indicates the The selected natural mode components;

[0072] The energy distribution of each selected natural mode component is ratioed to the total energy distribution of all selected natural mode components to obtain the energy ratio of each selected natural mode component. The energy ratios of all selected natural mode components are summed to obtain the turbidity fluctuation characteristic value.

[0073] The process nodes are divided into high emulsification risk areas and low emulsification risk areas, specifically including:

[0074] Determine whether the emulsification trend characteristic value of each process node is greater than or equal to the preset threshold. If so, it is recorded as a high emulsification risk area; if not, it is recorded as a low emulsification risk area.

[0075] In the high-risk early warning processing module, the high-risk early warning processing module triggers a real-time early warning mechanism based on the high emulsification risk area, specifically including:

[0076] In the high-risk early warning processing module, when the emulsification trend characteristic value is greater than or equal to the threshold, the system determines that the current process node is in a high-emulsification risk area and triggers a real-time early warning mechanism; the control system sends a warning signal through the sound and light alarm device, and a corresponding early warning prompt window pops up on the human-machine interface.

[0077] It should be noted that this module collects the interfacial tension and turbidity data of the mixed phase in the rare earth extraction process in real time, and extracts the interfacial tension anomaly characteristic values ​​and turbidity fluctuation characteristic values ​​respectively based on empirical mode decomposition and empirical wavelet transform technology, and then constructs normalized emulsification trend characteristic values, thereby realizing the dynamic identification and precise division of the emulsification state of the process node. This module fully combines the advantages of signal processing and multi-parameter fusion analysis to improve the accuracy and real-time performance of emulsification risk judgment. Compared with the traditional method that relies on manual experience or single parameter evaluation, the present invention can capture the changes in emulsification trends earlier and more sensitively, especially by introducing an automatic early warning mechanism based on the judgment of high emulsification risk areas, and by linking the sound and light alarms with the human-machine interface prompts through the control system, the safety and intelligence level of the rare earth extraction process are significantly improved, and it has good engineering application prospects and innovative value.

[0078] In the low-risk area emulsification trend prediction and adaptive control module, based on the low emulsification risk area, the interfacial tension anomaly characteristic values ​​and turbidity fluctuation characteristic values ​​of the mixed phase in the rare earth extraction process are extracted. The interfacial tension anomaly characteristic values ​​and turbidity fluctuation characteristic values ​​are constructed into a comprehensive risk characteristic vector and input into the emulsification development trend prediction model for analysis. The future emulsification development trend is predicted. Based on the prediction results, the extraction operation parameters are dynamically adjusted to achieve adaptive optimization control of the extraction process. Specifically,

[0079] The interfacial tension anomaly characteristic value and turbidity fluctuation characteristic value of the low emulsification risk area are obtained, and the interfacial tension anomaly characteristic value and the turbidity fluctuation characteristic value are constructed into a comprehensive risk characteristic vector as the input of the emulsification development trend prediction model to minimize the error between the predicted emulsification risk score and the actual emulsification risk score. The emulsification development trend prediction model is used as the prediction target, and the emulsification development trend model is trained. According to the trained emulsification development trend model, the predicted emulsification risk score is output. The emulsification development trend model is a support vector machine model.

[0080] The training process of the emulsification development trend prediction model is as follows:

[0081] During the model training phase, the interfacial tension anomaly characteristic values ​​and turbidity fluctuation characteristic values ​​of low-risk areas are first extracted from historical data, and these two characteristics are combined into a comprehensive risk characteristic vector as the model input; the actual historical emulsification risk score is used as the model output label, and the support vector machine regression algorithm is adopted with the radial basis function as the kernel function. By adjusting the penalty coefficient, kernel parameters and error tolerance, the optimal regression model is constructed. The goal is to minimize the error between the emulsification risk score predicted by the model and the actual score. The cross-validation strategy is introduced in the training process to optimize the hyperparameters, and the mean square error and determination coefficient indicators are used to evaluate the model performance. The trained support vector machine model is deployed to the control system, which receives the collected feature data in real time and outputs a predicted score for future emulsification risks, thereby realizing intelligent prediction and dynamic regulation of the emulsification phenomenon in the rare earth extraction process.

[0082] The prediction of future emulsification development trend specifically includes:

[0083] Determine whether the future emulsification risk score is greater than or equal to a preset threshold. If so, the future emulsification risk has a trend of changing from a low emulsification risk to a high emulsification risk. If not, the future emulsification risk does not have a trend of changing from a low emulsification risk to a high emulsification risk.

[0084] The method of dynamically adjusting the extraction operating parameters according to the prediction results to achieve adaptive optimization control of the extraction process specifically includes:

[0085] If the emulsification risk score output by the emulsification development trend prediction model is greater than or equal to the set threshold, the system automatically triggers the adaptive control mechanism to dynamically adjust the three key operating parameters: stirring rate, phase flow rate and demulsifier addition amount. Among them, the stirring rate is reduced in a step-by-step manner according to the rising trend of emulsification risk to reduce interphase disturbance and inhibit the formation of emulsion droplets. The phase flow rate is linearly adjusted according to the trend of abnormal interfacial tension changes to maintain two-phase flow balance. The demulsifier addition amount establishes a feedback control strategy based on the turbidity fluctuation characteristic value and the historical demulsification effect, and the addition ratio is increased as needed to enhance the demulsification efficiency.

[0086] During the dynamic adjustment process, the system uses a fuzzy PID control algorithm to collaboratively optimize the control of the above three operating parameters. It takes the emulsification risk score deviation and its change rate as input variables, and combines it with the preset empirical control rule library to generate corresponding control output signals, driving the actuator to accurately adjust the stirring motor speed, delivery pump frequency and metering pump dosing rate, thereby achieving real-time response to the emulsification phenomenon in the rare earth extraction process and process stability control, thereby improving the intelligence level and operational stability of the overall production process.

[0087] The working principle of the present invention is to achieve real-time monitoring, risk identification and intelligent regulation of emulsification phenomena during the extraction process. The system uses a real-time emulsification risk monitoring and classification module, a high-precision interfacial tension sensor and an optical turbidity detector to collect key parameters of the mixed phase online. Empirical mode decomposition and empirical wavelet transform techniques are used to extract interfacial tension anomaly eigenvalues ​​and turbidity fluctuation eigenvalues, respectively. These eigenvalues ​​are then normalized to obtain emulsification trend eigenvalues. Process nodes are then divided into high- and low-emulsification risk zones based on set thresholds. For high-risk zones, the system triggers audible and visual alarms and human-machine interface prompts for immediate warning. For low-risk zones, the low-risk zone emulsification trend prediction and adaptive control module constructs an emulsification development trend prediction model based on support vector machine regression. This model uses a comprehensive risk eigenvector as input to predict future emulsification risk scores and dynamically adjusts key operating parameters such as stirring rate, phase flow rate, and demulsifier addition accordingly. A fuzzy PID control algorithm is used to achieve multi-parameter coordinated optimization and adjustment, achieving the integrated control goals of intelligent identification, trend prediction, and adaptive regulation of emulsification phenomena in the rare earth extraction process. This significantly improves process stability, safety, and intelligence, demonstrating excellent industrial application value and technological innovation.

[0088] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A dynamic control system for rare earth extraction process control based on data acquisition, characterized in that: include: An emulsification risk real-time monitoring and classification module is used to collect real-time interfacial tension data and turbidity data of the mixed phase during the rare earth extraction process, dynamically analyze the data in the control system, and divide the process nodes into high emulsification risk areas and low emulsification risk areas based on the analysis results; A high-risk early warning processing module, which triggers a real-time early warning mechanism based on high emulsification risk areas; A low-risk area emulsification trend prediction and adaptive control module, which extracts interfacial tension anomaly characteristic values ​​and turbidity fluctuation characteristic values ​​of the mixed phase during the rare earth extraction process based on the low emulsification risk area, constructs the interfacial tension anomaly characteristic values ​​and turbidity fluctuation characteristic values ​​into a comprehensive risk characteristic vector, and inputs the vector into the emulsification development trend prediction model for analysis. The module predicts the future emulsification development trend and dynamically adjusts the extraction operating parameters based on the prediction results to achieve adaptive optimization control of the extraction process; The extraction operation parameters include stirring rate, phase flow rate and demulsifier addition amount.

2. The dynamic control system for rare earth extraction process control based on data acquisition according to claim 1 is characterized in that: The dynamic analysis of data in the control system specifically includes: Conduct trend analysis on interfacial tension and calculate abnormal characteristic value of interfacial tension based on its variation range; According to the change of the mixed phase turbidity, the turbidity fluctuation characteristic value is calculated; The interfacial tension anomaly characteristic value and the turbidity fluctuation characteristic value are normalized and calculated to obtain the emulsification trend characteristic value, which is used to divide the process nodes into high emulsification risk areas and low emulsification risk areas.

3. The dynamic control system for rare earth extraction process control based on data acquisition according to claim 2 is characterized in that: The process of obtaining the abnormal characteristic value of interfacial tension is as follows: Obtain real-time interfacial tension time series data during rare earth extraction; performing empirical mode decomposition on the interfacial tension time series to adaptively decompose it into a plurality of intrinsic mode function components and a trend residual term; Perform Hilbert transform on each intrinsic mode function component, construct an analytical signal and extract the instantaneous amplitude and instantaneous frequency information, and then calculate the energy density distribution of each intrinsic mode function; Select the energy fluctuation trend The intrinsic mode functions are calculated, and the difference between the maximum and minimum energy density of these intrinsic mode functions is calculated to obtain the energy density deviation value. The energy density deviation value is compared with the selected previous The energy mean of the intrinsic mode functions is calculated by ratio, and the abnormal characteristic value of the interfacial tension is obtained.

4. The dynamic control system for rare earth extraction process control based on data acquisition according to claim 2 is characterized in that: The acquisition process of the turbidity fluctuation characteristic value is: Obtaining real-time mixed phase turbidity time series data during rare earth extraction; The mixed phase turbidity time series data were decomposed by empirical wavelet transform to obtain a set of intrinsic mode components. Select multiple modal components reflecting turbidity fluctuation characteristics and calculate the energy distribution of the selected modal components; The energy distribution of each selected natural mode component is ratioed to the total energy distribution of all selected natural mode components to obtain the energy ratio of each selected natural mode component. The energy ratios of all selected natural mode components are summed to obtain the turbidity fluctuation characteristic value.

5. The dynamic control system for rare earth extraction process control based on data acquisition according to claim 1 is characterized in that: The process nodes are divided into high emulsification risk areas and low emulsification risk areas, specifically including: Determine whether the emulsification trend characteristic value of each process node is greater than or equal to the preset threshold. If so, it is recorded as a high emulsification risk area; if not, it is recorded as a low emulsification risk area.

6. The dynamic control system for rare earth extraction process control based on data acquisition according to claim 1 is characterized in that: The interfacial tension abnormality characteristic value and turbidity fluctuation characteristic value are constructed into a comprehensive risk characteristic vector and input into the emulsification development trend prediction model for analysis, specifically including: The interfacial tension anomaly characteristic value and turbidity fluctuation characteristic value of the low emulsification risk area are obtained, and the interfacial tension anomaly characteristic value and the turbidity fluctuation characteristic value are constructed into a comprehensive risk characteristic vector as the input of the emulsification development trend prediction model to minimize the error between the predicted emulsification risk score and the actual emulsification risk score. The emulsification development trend prediction model is used as the prediction target, and the emulsification development trend model is trained. According to the trained emulsification development trend model, the predicted emulsification risk score is output. The emulsification development trend model is a support vector machine model.

7. The dynamic control system for rare earth extraction process control based on data acquisition according to claim 6, characterized in that: The training process of the emulsification development trend prediction model is as follows: During the model training phase, the interfacial tension anomaly characteristic values ​​and turbidity fluctuation characteristic values ​​of low-risk areas are first extracted from historical data and constructed into a comprehensive risk characteristic vector as model input; the actual historical emulsification risk score is used as the model output label, and the support vector machine regression algorithm is adopted with the radial basis function as the kernel function. By adjusting the penalty coefficient, kernel parameters and error tolerance, the optimal regression model is constructed. The goal is to minimize the error between the emulsification risk score predicted by the model and the actual score. The cross-validation strategy is introduced during the training process to optimize the hyperparameters, and the mean square error and determination coefficient indicators are used to evaluate the model performance. The trained support vector machine model is deployed to the control system, which receives the collected feature data in real time and outputs a predicted score for future emulsification risks, thereby realizing intelligent prediction and dynamic regulation of the emulsification phenomenon in the rare earth extraction process.

8. The dynamic control system for rare earth extraction process control based on data acquisition according to claim 1 is characterized in that: The prediction of future emulsification development trend specifically includes: Determine whether the future emulsification risk score is greater than or equal to a preset threshold. If so, the future emulsification risk has a trend of changing from a low emulsification risk to a high emulsification risk. If not, the future emulsification risk does not have a trend of changing from a low emulsification risk to a high emulsification risk.

9. The dynamic control system for rare earth extraction process control based on data acquisition according to claim 1, characterized in that: The method of dynamically adjusting the extraction operating parameters according to the prediction results to achieve adaptive optimization control of the extraction process specifically includes: If the emulsification risk score output by the emulsification development trend prediction model is greater than or equal to the set threshold, the system automatically triggers the adaptive control mechanism to dynamically adjust the three key operating parameters: stirring rate, phase flow rate and demulsifier addition amount. Among them, the stirring rate is reduced in a step-by-step manner according to the rising trend of emulsification risk to reduce interphase disturbance and inhibit the formation of emulsion droplets. The phase flow rate is linearly adjusted according to the trend of abnormal interfacial tension changes to maintain two-phase flow balance. The demulsifier addition amount establishes a feedback control strategy based on the turbidity fluctuation characteristic value and the historical demulsification effect, and the addition ratio is increased as needed to enhance the demulsification efficiency.

Images